Computer vision techniques to determine the health status in broccoli plantations

The demand for broccoli has increased significantly in the last years due to the benefits of its consumption for human health. This poses new challenges for producers, who increasingly rely on technology to improve production processes, increase yields and thereby meet the current demand. One of the...

Descripción completa

Detalles Bibliográficos
Autores: Caina, Darwin, Carillo, René, Carrillo, Marcelo
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2017
País:Ecuador
Institución:Universidad Central del Ecuador
Repositorio:Revista Siembra
Idioma:español
OAI Identifier:oai:revistadigital.uce.edu.ec:article/499
Acceso en línea:https://revistadigital.uce.edu.ec/index.php/SIEMBRA/article/view/499
Access Level:acceso abierto
Palabra clave:Visión computacional
brócoli
procesamiento de imágenes
OpenCV
HSV
Computer vision
broccoli
digital image processing
Descripción
Sumario:The demand for broccoli has increased significantly in the last years due to the benefits of its consumption for human health. This poses new challenges for producers, who increasingly rely on technology to improve production processes, increase yields and thereby meet the current demand. One of the technology fields that has gained interest in crop production the use of Computer Vision models, which can provide support and assistance in food production. This paper proposes an algorithm based on color detection of broccoli, which, at the macro level can identify phytosanitary problems in broccoli plantations; and, at the micro level can be used to identify the product that is suitable for consumption. The algorithm uses open source tools such as OpenCV and Python, so that it can be developed at low cost with results similar or better than those obtained with commercial softwares.